MendixMau/mxcli-project-toolkit
Shared Mendix migration skills, prompt templates, and bug logs — used across all projects
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit MendixMau/mxcli-project-toolkit/.claude ./rig-mxcli-project-toolkit # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/architect-agent.md https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/master/agents/architect-agent.md $ curl -fsSL --create-dirs -o .claude/agents/ba-agent.md https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/master/agents/ba-agent.md $ curl -fsSL --create-dirs -o .claude/agents/gate-agent.md https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/master/agents/gate-agent.md $ curl -fsSL --create-dirs -o .claude/agents/mdl-agent.md https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/master/agents/mdl-agent.md $ curl -fsSL --create-dirs -o .claude/agents/review-agent.md https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/master/agents/review-agent.md $ curl -fsSL --create-dirs -o .claude/agents/test-agent.md https://raw.githubusercontent.com/MendixMau/mxcli-project-toolkit/master/agents/test-agent.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (6)
| architect-agent model: opus | Owns Stage 3 (Architecture & Design) and Stage 4 (Build Plan) for {{PROJECT}} — module boundaries, blueprint, fit-gap, build plan. Use once BRDs are validation-clean. Never touches mxcli. |
| ba-agent model: sonnet | Owns discovery and interview gates for {{PROJECT}} (conversion-runbook.md Stages P, 0-2, 7). Use for intake, triage, extraction, requirements gathering, and any decision that needs a proposal-with-evi |
| gate-agent model: sonnet | Runs {{PROJECT}}'s build/quality gates after a script has been executed against the .mpr, and reports pass/fail with a digested error list. Use after any mxcli exec, not before. |
| mdl-agent model: sonnet | Drafts and syntax-validates mxcli MDL scripts for {{PROJECT}}. Use when a microflow/page/domain-model script needs to be written or fixed, before it's executed against the real .mpr. |
| review-agent model: sonnet | Closes a module in {{PROJECT}}. Two jobs: (1) catches behaviorally-equivalent, architecturally-wrong drift that mxbuild and e2e cannot see — a module imported but never wired in, a ledger row whose cl |
| test-agent model: sonnet | Authors and runs e2e test specs for {{PROJECT}} against the running app, grounded in BRDs, module briefs and the live model — not guessed selectors. Use after a gate-agent pass, once a feature is expe |
Slash commands (3)
/mobile-auto-test-prompt/mobile-dev-loop-prompt/toolkit-init
Similar rigs
anthropics/claude-agent-sdk-python
—
Pragmatist 1.1k tok ·
jmckinley/claude-code-resources
Complete guide and automation for Claude Code
Pragmatist 68 tok ·
chamirusenarath96/spec-driven-sdlc-template
Spec-driven, agent-run SDLC template: GitHub Issues/Projects + Claude Code subagents + gh-aw agentic workflows
Minimalist 1.5k tok ·
vtomasv/sdd-dev-template
Portable Spec-Driven Development (SDD) template with Docker Compose, Claude/Gemini/OpenAI agent-ready workflows, brownfield/greenfield bootstrapping, and Human-in-the-Loop (HITL) guardrails for safe, scalable coding.
Minimalist 41 tok ·